Deep learning enables accurate brain tissue microstructure analysis based on clinically feasible diffusion magnetic resonance imaging
Yuxing Li,
Zhizheng Zhuo,
Chenghao Liu,
Yunyun Duan,
Yulu Shi,
Tingting Wang,
Runzhi Li,
Yanli Wang,
Jiwei Jiang,
Jun Xu,
Decai Tian,
Xinghu Zhang,
Fudong Shi,
Xiaofeng Zhang,
Aaron Carass,
Frederik Barkhof,
Jerry L Prince,
Chuyang Ye,
Yaou Liu
Affiliations
Yuxing Li
School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China
Zhizheng Zhuo
Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Chenghao Liu
School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China
Yunyun Duan
Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Yulu Shi
Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Tingting Wang
Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Runzhi Li
Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China; China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
Yanli Wang
Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China; China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
Jiwei Jiang
Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China; China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China
Jun Xu
Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Decai Tian
Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China; China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China; Advanced Innovation Center for Human Brain Protection, Capital Medical University, Beijing, China
Xinghu Zhang
Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Fudong Shi
Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China; China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China; Department of Neurology and Tianjin Neurological Institute, Tianjin Medical University General Hospital, Tianjin, China
Xiaofeng Zhang
School of Information and Electronics, Beijing Institute of Technology, Zhuhai, China
Aaron Carass
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, USA
Frederik Barkhof
Department of Radiology and Nuclear Medicine, Amsterdam University Medical Center, Amsterdam, 1081 HV, the Netherlands
Jerry L Prince
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, USA
Chuyang Ye
School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China; Corresponding authors at: No. 5, Zhongguancun South Street, Haidian District, Beijing, 100081 PR China.
Yaou Liu
Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China; Corresponding authors at: No.119, South Fourth Ring West Road, Fengtai District, Beijing, 100070 PR China.
Diffusion magnetic resonance imaging (dMRI) allows non-invasive assessment of brain tissue microstructure. Current model-based tissue microstructure reconstruction techniques require a large number of diffusion gradients, which is not clinically feasible due to imaging time constraints, and this has limited the use of tissue microstructure information in clinical settings. Recently, approaches based on deep learning (DL) have achieved promising tissue microstructure reconstruction results using clinically feasible dMRI. However, it remains unclear whether the subtle tissue changes associated with disease or age are properly preserved with DL approaches and whether DL reconstruction results can benefit clinical applications. Here, we provide the first evidence that DL approaches to tissue microstructure reconstruction yield reliable brain tissue microstructure analysis based on clinically feasible dMRI scans. Specifically, we reconstructed tissue microstructure from four different brain dMRI datasets with only 12 diffusion gradients, a clinically feasible protocol, and the neurite orientation dispersion and density imaging (NODDI) and spherical mean technique (SMT) models were considered. With these results we show that disease-related and age-dependent alterations of brain tissue were accurately identified. These findings demonstrate that DL tissue microstructure reconstruction can accurately quantify microstructural alterations in the brain based on clinically feasible dMRI.
